Differentiable Histogram with Hard-Binning

Abstract

The simplicity and expressiveness of a histogram render it a useful feature in different contexts including deep learning. Although the process of computing a histogram is non-differentiable, researchers have proposed differentiable approximations, which have some limitations. A differentiable histogram that directly approximates the hard-binning operation in conventional histograms is proposed. It combines the strength of existing differentiable histograms and overcomes their individual challenges. In comparison to a histogram computed using Numpy, the proposed histogram has an absolute approximation error of 0.000158.

arXiv commentAccepted at Blacks in AI Workshop, NeurIPS 2020

References in corpus (2)

• Histogram Layers for Texture Analysis
• DeepHist: Differentiable Joint and Color Histogram Layers for Image-to-Image Translation

Cited by in corpus (1)

• Histogram Layers for Synthetic Aperture Sonar Imagery